CtrlK
BlogDocsLog inGet started
Tessl Logo

openspec-explore

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is actionable and well-structured with concrete commands and a clear change-handling sequence. The main drag is conciseness — illustrative dialog vignettes restate the stance and could be trimmed.

Suggestions

Trim or compress the multi-block ASCII conversation vignettes; one short example conveys the stance without restating it across four scenarios.

Fold 'What You Don't Have To Do' into 'The Stance' to avoid restating the same anti-patterns twice.

Keep concrete commands and the capture table as-is — they are the highest-value content.

DimensionReasoningScore

Conciseness

Mostly efficient guidance, but long ASCII dialog vignettes ('User brings a vague idea', 'The auth system is a mess') and 'What You Don't Have To Do' restate the stance; could be tightened to leaner tokens.

2 / 3

Actionability

Concrete commands (`openspec list --json`, `/opsx:new`, `/opsx:ff`), specific file paths, and an insight→artifact capture table give copy-ready, executable guidance.

3 / 3

Workflow Clarity

Intentionally a stance not a workflow, but the 'When a change exists' branch is explicitly sequenced (steps 1–4) with an offer/don't-auto-capture checkpoint; no destructive ops need validation loops.

3 / 3

Progressive Disclosure

Single self-contained file with no bundle, organized into well-signaled sections separated by `---` and headers; no nested references to penalize.

3 / 3

Total

11

/

12

Passed

Description

77%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description cleanly covers what and when with third-person voice and a distinct niche. Trigger term coverage is the weakest area — it lacks common phrasings users might naturally say.

Suggestions

Broaden trigger terms to natural phrasings users actually say, e.g. 'brainstorm', 'spike', 'talk through an idea', or 'design before building'.

Keep the 'Use when...' clause explicit but consider pairing it with a concrete example trigger to strengthen natural-keyword coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('exploring ideas, investigating problems, and clarifying requirements') alongside the named mode; not abstract enough to drop to 2.

3 / 3

Completeness

Clearly states what ('thinking partner for exploring ideas...') and gives an explicit 'Use when the user wants to think through something before or during a change.'

3 / 3

Trigger Term Quality

Includes natural phrasing like 'think through something' but misses common variations users would say (brainstorm, spike, talk through, design); not bare enough for 1.

2 / 3

Distinctiveness Conflict Risk

'explore mode' tied to before/during-a-change framing carves a distinct niche unlikely to trigger for the wrong skill.

3 / 3

Total

11

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Draculabo/AntigravityManager
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.